Skip to main content
Glama

Find elements

browser_find
Read-only

Locate page elements by their visible words or labels, including off-screen targets, and return their references ranked by best match. Use it to find buttons, inputs, or links before acting.

Instructions

Refs of elements anywhere on the page, outside the visible screen too, by the words they show or are labelled with, best match first. Separate several targets by commas.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "browser_find"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesWords naming the element(s), e.g. "Sort by" or "price max input, Go button"

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe read (readOnlyHint true, destructiveHint false, openWorldHint true), so the description does not need to re-establish safety. It does add real behavioral context beyond them: the search extends outside the visible screen, results are ranked with the best match first, and multiple targets can be requested at once. What it omits is the failure mode — what comes back when nothing matches — and whether returned refs stay valid across later snapshots or navigation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler, and the most important fact (it finds refs anywhere on the page by displayed text) leads. The opening noun fragment reads awkwardly and could be tightened into a verb-first sentence, but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only lookup with no output schema, the description covers the essentials an agent needs: what it returns (refs), the matching basis (displayed or label text), the search scope (including off-screen), result ordering, and multi-target syntax. Only edge-case behavior — no-match results and ref validity lifetime — is left unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With a single parameter at 100% schema description coverage, the schema already carries the meaning and even shows comma-separated multi-target examples. The description's contribution is reinforcing the comma convention for several targets and the ranking of results, which is mildly useful but largely duplicative of the schema's own example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource and operation: it returns element refs matched by visible text or accessible label, and explicitly notes the search covers off-screen content as well as the visible viewport. That scope statement distinguishes it usefully from a viewport-bound snapshot or query, though the phrasing is a noun fragment rather than a crisp verb statement ('find/locate element refs by text').

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: an agent can infer this is the tool to reach for when it knows an element's text but not its ref, and 'best match first' hints at its role as a lookup ahead of click/type. There is no explicit when-to-use, when-not-to-use, or named alternative such as browser_query or browser_snapshot, so the agent must infer the boundary itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.